Fokker--Planck Particle Systems for Bayesian Inference: Computational Approaches

DOI10.1137/19M1303162zbMath1473.65274arXiv1911.10832OpenAlexW3158386662MaRDI QIDQ4995111

Simon Weissmann, Sebastian Reich

Publication date: 23 June 2021

Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1911.10832

zbMATH Keywords

Fokker-Planck equationgradient flowlocalizationBayesian inverse problemsaffine invariancegradient-free sampling methods

Mathematics Subject Classification ID

Probabilistic methods, particle methods, etc. for boundary value problems involving PDEs (65N75) Bayesian inference (62F15) Derivative-free methods and methods using generalized derivatives (90C56) Numerical solutions to stochastic differential and integral equations (65C30) Numerical methods for inverse problems for boundary value problems involving PDEs (65N21)

Related Items (15)

Projected Wasserstein Gradient Descent for High-Dimensional Bayesian Inference ⋮ Derivative-Free Bayesian Inversion Using Multiscale Dynamics ⋮ Continuous Time Limit of the Stochastic Ensemble Kalman Inversion: Strong Convergence Analysis ⋮ GP-ETAS: semiparametric Bayesian inference for the spatio-temporal epidemic type aftershock sequence model ⋮ Adaptive Tikhonov strategies for stochastic ensemble Kalman inversion ⋮ Neural Parametric Fokker--Planck Equation ⋮ Ensemble Inference Methods for Models With Noisy and Expensive Likelihoods ⋮ Iterated Kalman methodology for inverse problems ⋮ Consensus‐based sampling ⋮ Component-wise iterative ensemble Kalman inversion for static Bayesian models with unknown measurement error covariance ⋮ Affine-invariant ensemble transform methods for logistic regression ⋮ Ensemble Kalman inversion for nonlinear problems: weights, consistency, and variance bounds ⋮ Propagation of chaos: a review of models, methods and applications. II: Applications ⋮ The Ensemble Kalman Filter for Rare Event Estimation ⋮ Gradient flow structure and convergence analysis of the ensemble Kalman inversion for nonlinear forward models

Uses Software

• EnKF
• EnsembleQN

Cites Work

• Ensemble samplers with affine invariance
• A dynamical systems framework for intermittent data assimilation
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• Ensemble preconditioning for Markov chain Monte Carlo simulation
• A blob method for diffusion
• Statistical and computational inverse problems.
• Discrete gradients for computational Bayesian inference
• Kinetic methods for inverse problems
• Ensemble Kalman methods for inverse problems
• Inverse problems: A Bayesian perspective
• Sequential Monte Carlo Methods for High-Dimensional Inverse Problems: A Case Study for the Navier--Stokes Equations
• Introduction to Uncertainty Quantification
• Deterministic diffusion of particles
• A Deterministic Approximation of Diffusion Equations Using Particles
• Sequential Monte Carlo Samplers
• Analysis of the Ensemble and Polynomial Chaos Kalman Filters in Bayesian Inverse Problems
• The Variational Formulation of the Fokker--Planck Equation
• Data-Driven Computational Methods
• Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
• Riemann Manifold Langevin and Hamiltonian Monte Carlo Methods
• Optimization Methods for Large-Scale Machine Learning
• Affine Invariant Interacting Langevin Dynamics for Bayesian Inference
• Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler
• Stochastic Processes and Applications
• Probabilistic Forecasting and Bayesian Data Assimilation
• Ensemble Kalman inversion: a derivative-free technique for machine learning tasks
• Well posedness and convergence analysis of the ensemble Kalman inversion
• Data assimilation: The Schrödinger perspective
• Data Assimilation
• Analysis of the Ensemble Kalman Filter for Inverse Problems
• All of Nonparametric Statistics
• Data Assimilation
• MCMC methods for functions: modifying old algorithms to make them faster
• Unnamed Item

This page was built for publication: Fokker--Planck Particle Systems for Bayesian Inference: Computational Approaches